tflite-support icon indicating copy to clipboard operation
tflite-support copied to clipboard

TFLite Support is a toolkit that helps users to develop ML and deploy TFLite models onto mobile / ioT devices.

Results 112 tflite-support issues
Sort by recently updated
recently updated
newest added

Hi all, could you please consider documenting which parts of tflite-support are to be considered superseded by MediaPipe? It has been mentioned multiple times that MediaPipe is what you are...

I'm trying to install 0.4.4 on the latest Rasbian OS (Arm64), that has Python 3.11. It fails because there are no version for Python 3.11, only for 3.9 and older....

My model is trained on a certain mean and std: mean = [151.2405, 119.5950, 107.8395] std = [63.0105, 56.4570, 55.0035] The problem is that the attempt to add these values...

Hi my friends, I'm using Colab (with python3.10 ) for model training. I tried to use both tflite-support or tflite_support_nightly like this: But I got this error: Please give me...

In the Bert QA testcase provided by README.md, I think the context is seperated by different types of whitespace. I also print the results of the subwords of tokens. It...

My arch is special and install by whl failed, I wanna try source compinling but don't know how to do.

The wheel file for x86 is available, but we need the one for aarch64, would you mind sharing that in pypi.

Hi, I hope I am correct here, a docker I have been using without problems for the past months started throwing an error today. The only difference I have noted...

YOLOv8 TFLite export is failing with the latest release of `tensorflow==2.14.0` but works with `tensorflow==2.13.1`, the prior release. The error originates from the `tflite_support` package. ```python Traceback (most recent call...

I am quantizing my yolov5 model with tflite using the following code : import tensorflow as tf saved_model_dir ='path2_saved_model' converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir) converter.optimizations = [tf.lite.Optimize.DEFAULT] converter.representative_dataset = representative_dataset converter.target_spec.supported_ops =...